Ledger is proposed, a deterministic runtime layer that distills an agent's completed interactions into an explicit execution state: what has been observed, what has been modified, and what has been attempted, in an online execution ledger and applies it at two boundaries of every step.
Zehao Wang, Yisen Xu, Cheng-Lin Li et al.· 2 citations
An LLM-based multi-agent framework to generate performance-oriented tests that expose runtime differences more effectively than the original tests is proposed, which uses three separate agents to generate, diagnose, and repair deterministic tests that preserve functional correctness while better exposing performance di...
Nhat Minh Lê, Yisen Xu, Zhijie Wang et al.· arXiv.org· 0 citations
STAIR is introduced, a framework that converts historical repair trajectories into hierarchical, reusable plans that can be adapted to steer future repairs, and it is shown that mixing multiple abstraction levels surpasses any single level and that raw, unabstracted trajectories transfer substantially worse.
Yisen Xu, Jiayuan Zhou, Ruiqi Pan et al.· arXiv.org· 0 citations
ECLoop is presented, an execution layer that interposes between the agent and the repository to enforce evidence-conditioned execution and shows that each of ECLoop's three operations contributes distinct value and that structured evidence conditions outperform an equivalent natural-language summary.
Yisen Xu, Chenglin Li, Zehao Wang et al.· arXiv.org· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
